summaryrefslogtreecommitdiffstats
path: root/drivers/gpu/drm/amd/amdgpu/amdgpu_mn.c
blob: 3e6823fdd93942cce3ace2c21b456f1e4e1d8d84 (plain)
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
/*
 * Copyright 2014 Advanced Micro Devices, Inc.
 * All Rights Reserved.
 *
 * Permission is hereby granted, free of charge, to any person obtaining a
 * copy of this software and associated documentation files (the
 * "Software"), to deal in the Software without restriction, including
 * without limitation the rights to use, copy, modify, merge, publish,
 * distribute, sub license, and/or sell copies of the Software, and to
 * permit persons to whom the Software is furnished to do so, subject to
 * the following conditions:
 *
 * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
 * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
 * FITNESS FOR A PARTICULAR PURPOSE AND NON-INFRINGEMENT. IN NO EVENT SHALL
 * THE COPYRIGHT HOLDERS, AUTHORS AND/OR ITS SUPPLIERS BE LIABLE FOR ANY CLAIM,
 * DAMAGES OR OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR
 * OTHERWISE, ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE
 * USE OR OTHER DEALINGS IN THE SOFTWARE.
 *
 * The above copyright notice and this permission notice (including the
 * next paragraph) shall be included in all copies or substantial portions
 * of the Software.
 *
 */
/*
 * Authors:
 *    Christian König <christian.koenig@amd.com>
 */

/**
 * DOC: MMU Notifier
 *
 * For coherent userptr handling registers an MMU notifier to inform the driver
 * about updates on the page tables of a process.
 *
 * When somebody tries to invalidate the page tables we block the update until
 * all operations on the pages in question are completed, then those pages are
 * marked as accessed and also dirty if it wasn't a read only access.
 *
 * New command submissions using the userptrs in question are delayed until all
 * page table invalidation are completed and we once more see a coherent process
 * address space.
 */

#include <linux/firmware.h>
#include <linux/module.h>
#include <linux/mmu_notifier.h>
#include <linux/interval_tree.h>
#include <drm/drmP.h>
#include <drm/drm.h>

#include "amdgpu.h"
#include "amdgpu_amdkfd.h"

/**
 * struct amdgpu_mn
 *
 * @adev: amdgpu device pointer
 * @mm: process address space
 * @mn: MMU notifier structure
 * @type: type of MMU notifier
 * @work: destruction work item
 * @node: hash table node to find structure by adev and mn
 * @lock: rw semaphore protecting the notifier nodes
 * @objects: interval tree containing amdgpu_mn_nodes
 * @read_lock: mutex for recursive locking of @lock
 * @recursion: depth of recursion
 *
 * Data for each amdgpu device and process address space.
 */
struct amdgpu_mn {
	/* constant after initialisation */
	struct amdgpu_device	*adev;
	struct mm_struct	*mm;
	struct mmu_notifier	mn;
	enum amdgpu_mn_type	type;

	/* only used on destruction */
	struct work_struct	work;

	/* protected by adev->mn_lock */
	struct hlist_node	node;

	/* objects protected by lock */
	struct rw_semaphore	lock;
	struct rb_root_cached	objects;
	struct mutex		read_lock;
	atomic_t		recursion;
};

/**
 * struct amdgpu_mn_node
 *
 * @it: interval node defining start-last of the affected address range
 * @bos: list of all BOs in the affected address range
 *
 * Manages all BOs which are affected of a certain range of address space.
 */
struct amdgpu_mn_node {
	struct interval_tree_node	it;
	struct list_head		bos;
};

/**
 * amdgpu_mn_destroy - destroy the MMU notifier
 *
 * @work: previously sheduled work item
 *
 * Lazy destroys the notifier from a work item
 */
static void amdgpu_mn_destroy(struct work_struct *work)
{
	struct amdgpu_mn *amn = container_of(work, struct amdgpu_mn, work);
	struct amdgpu_device *adev = amn->adev;
	struct amdgpu_mn_node *node, *next_node;
	struct amdgpu_bo *bo, *next_bo;

	mutex_lock(&adev->mn_lock);
	down_write(&amn->lock);
	hash_del(&amn->node);
	rbtree_postorder_for_each_entry_safe(node, next_node,
					     &amn->objects.rb_root, it.rb) {
		list_for_each_entry_safe(bo, next_bo, &node->bos, mn_list) {
			bo->mn = NULL;
			list_del_init(&bo->mn_list);
		}
		kfree(node);
	}
	up_write(&amn->lock);
	mutex_unlock(&adev->mn_lock);
	mmu_notifier_unregister_no_release(&amn->mn, amn->mm);
	kfree(amn);
}

/**
 * amdgpu_mn_release - callback to notify about mm destruction
 *
 * @mn: our notifier
 * @mm: the mm this callback is about
 *
 * Shedule a work item to lazy destroy our notifier.
 */
static void amdgpu_mn_release(struct mmu_notifier *mn,
			      struct mm_struct *mm)
{
	struct amdgpu_mn *amn = container_of(mn, struct amdgpu_mn, mn);

	INIT_WORK(&amn->work, amdgpu_mn_destroy);
	schedule_work(&amn->work);
}


/**
 * amdgpu_mn_lock - take the write side lock for this notifier
 *
 * @mn: our notifier
 */
void amdgpu_mn_lock(struct amdgpu_mn *mn)
{
	if (mn)
		down_write(&mn->lock);
}

/**
 * amdgpu_mn_unlock - drop the write side lock for this notifier
 *
 * @mn: our notifier
 */
void amdgpu_mn_unlock(struct amdgpu_mn *mn)
{
	if (mn)
		up_write(&mn->lock);
}

/**
 * amdgpu_mn_read_lock - take the read side lock for this notifier
 *
 * @amn: our notifier
 */
static int amdgpu_mn_read_lock(struct amdgpu_mn *amn, bool blockable)
{
	if (blockable)
		mutex_lock(&amn->read_lock);
	else if (!mutex_trylock(&amn->read_lock))
		return -EAGAIN;

	if (atomic_inc_return(&amn->recursion) == 1)
		down_read_non_owner(&amn->lock);
	mutex_unlock(&amn->read_lock);

	return 0;
}

/**
 * amdgpu_mn_read_unlock - drop the read side lock for this notifier
 *
 * @amn: our notifier
 */
static void amdgpu_mn_read_unlock(struct amdgpu_mn *amn)
{
	if (atomic_dec_return(&amn->recursion) == 0)
		up_read_non_owner(&amn->lock);
}

/**
 * amdgpu_mn_invalidate_node - unmap all BOs of a node
 *
 * @node: the node with the BOs to unmap
 * @start: start of address range affected
 * @end: end of address range affected
 *
 * Block for operations on BOs to finish and mark pages as accessed and
 * potentially dirty.
 */
static void amdgpu_mn_invalidate_node(struct amdgpu_mn_node *node,
				      unsigned long start,
				      unsigned long end)
{
	struct amdgpu_bo *bo;
	long r;

	list_for_each_entry(bo, &node->bos, mn_list) {

		if (!amdgpu_ttm_tt_affect_userptr(bo->tbo.ttm, start, end))
			continue;

		r = reservation_object_wait_timeout_rcu(bo->tbo.resv,
			true, false, MAX_SCHEDULE_TIMEOUT);
		if (r <= 0)
			DRM_ERROR("(%ld) failed to wait for user bo\n", r);

		amdgpu_ttm_tt_mark_user_pages(bo->tbo.ttm);
	}
}

/**
 * amdgpu_mn_invalidate_range_start_gfx - callback to notify about mm change
 *
 * @mn: our notifier
 * @range: mmu notifier context
 *
 * Block for operations on BOs to finish and mark pages as accessed and
 * potentially dirty.
 */
static int amdgpu_mn_invalidate_range_start_gfx(struct mmu_notifier *mn,
			const struct mmu_notifier_range *range)
{
	struct amdgpu_mn *amn = container_of(mn, struct amdgpu_mn, mn);
	struct interval_tree_node *it;
	unsigned long end;

	/* notification is exclusive, but interval is inclusive */
	end = range->end - 1;

	/* TODO we should be able to split locking for interval tree and
	 * amdgpu_mn_invalidate_node
	 */
	if (amdgpu_mn_read_lock(amn, range->blockable))
		return -EAGAIN;

	it = interval_tree_iter_first(&amn->objects, range->start, end);
	while (it) {
		struct amdgpu_mn_node *node;

		if (!range->blockable) {
			amdgpu_mn_read_unlock(amn);
			return -EAGAIN;
		}

		node = container_of(it, struct amdgpu_mn_node, it);
		it = interval_tree_iter_next(it, range->start, end);

		amdgpu_mn_invalidate_node(node, range->start, end);
	}

	return 0;
}

/**
 * amdgpu_mn_invalidate_range_start_hsa - callback to notify about mm change
 *
 * @mn: our notifier
 * @mm: the mm this callback is about
 * @start: start of updated range
 * @end: end of updated range
 *
 * We temporarily evict all BOs between start and end. This
 * necessitates evicting all user-mode queues of the process. The BOs
 * are restorted in amdgpu_mn_invalidate_range_end_hsa.
 */
static int amdgpu_mn_invalidate_range_start_hsa(struct mmu_notifier *mn,
			const struct mmu_notifier_range *range)
{
	struct amdgpu_mn *amn = container_of(mn, struct amdgpu_mn, mn);
	struct interval_tree_node *it;
	unsigned long end;

	/* notification is exclusive, but interval is inclusive */
	end = range->end - 1;

	if (amdgpu_mn_read_lock(amn, range->blockable))
		return -EAGAIN;

	it = interval_tree_iter_first(&amn->objects, range->start, end);
	while (it) {
		struct amdgpu_mn_node *node;
		struct amdgpu_bo *bo;

		if (!range->blockable) {
			amdgpu_mn_read_unlock(amn);
			return -EAGAIN;
		}

		node = container_of(it, struct amdgpu_mn_node, it);
		it = interval_tree_iter_next(it, range->start, end);

		list_for_each_entry(bo, &node->bos, mn_list) {
			struct kgd_mem *mem = bo->kfd_bo;

			if (amdgpu_ttm_tt_affect_userptr(bo->tbo.ttm,
							 range->start,
							 end))
				amdgpu_amdkfd_evict_userptr(mem, range->mm);
		}
	}

	return 0;
}

/**
 * amdgpu_mn_invalidate_range_end - callback to notify about mm change
 *
 * @mn: our notifier
 * @mm: the mm this callback is about
 * @start: start of updated range
 * @end: end of updated range
 *
 * Release the lock again to allow new command submissions.
 */
static void amdgpu_mn_invalidate_range_end(struct mmu_notifier *mn,
			const struct mmu_notifier_range *range)
{
	struct amdgpu_mn *amn = container_of(mn, struct amdgpu_mn, mn);

	amdgpu_mn_read_unlock(amn);
}

static const struct mmu_notifier_ops amdgpu_mn_ops[] = {
	[AMDGPU_MN_TYPE_GFX] = {
		.release = amdgpu_mn_release,
		.invalidate_range_start = amdgpu_mn_invalidate_range_start_gfx,
		.invalidate_range_end = amdgpu_mn_invalidate_range_end,
	},
	[AMDGPU_MN_TYPE_HSA] = {
		.release = amdgpu_mn_release,
		.invalidate_range_start = amdgpu_mn_invalidate_range_start_hsa,
		.invalidate_range_end = amdgpu_mn_invalidate_range_end,
	},
};

/* Low bits of any reasonable mm pointer will be unused due to struct
 * alignment. Use these bits to make a unique key from the mm pointer
 * and notifier type.
 */
#define AMDGPU_MN_KEY(mm, type) ((unsigned long)(mm) + (type))

/**
 * amdgpu_mn_get - create notifier context
 *
 * @adev: amdgpu device pointer
 * @type: type of MMU notifier context
 *
 * Creates a notifier context for current->mm.
 */
struct amdgpu_mn *amdgpu_mn_get(struct amdgpu_device *adev,
				enum amdgpu_mn_type type)
{
	struct mm_struct *mm = current->mm;
	struct amdgpu_mn *amn;
	unsigned long key = AMDGPU_MN_KEY(mm, type);
	int r;

	mutex_lock(&adev->mn_lock);
	if (down_write_killable(&mm->mmap_sem)) {
		mutex_unlock(&adev->mn_lock);
		return ERR_PTR(-EINTR);
	}

	hash_for_each_possible(adev->mn_hash, amn, node, key)
		if (AMDGPU_MN_KEY(amn->mm, amn->type) == key)
			goto release_locks;

	amn = kzalloc(sizeof(*amn), GFP_KERNEL);
	if (!amn) {
		amn = ERR_PTR(-ENOMEM);
		goto release_locks;
	}

	amn->adev = adev;
	amn->mm = mm;
	init_rwsem(&amn->lock);
	amn->type = type;
	amn->mn.ops = &amdgpu_mn_ops[type];
	amn->objects = RB_ROOT_CACHED;
	mutex_init(&amn->read_lock);
	atomic_set(&amn->recursion, 0);

	r = __mmu_notifier_register(&amn->mn, mm);
	if (r)
		goto free_amn;

	hash_add(adev->mn_hash, &amn->node, AMDGPU_MN_KEY(mm, type));

release_locks:
	up_write(&mm->mmap_sem);
	mutex_unlock(&adev->mn_lock);

	return amn;

free_amn:
	up_write(&mm->mmap_sem);
	mutex_unlock(&adev->mn_lock);
	kfree(amn);

	return ERR_PTR(r);
}

/**
 * amdgpu_mn_register - register a BO for notifier updates
 *
 * @bo: amdgpu buffer object
 * @addr: userptr addr we should monitor
 *
 * Registers an MMU notifier for the given BO at the specified address.
 * Returns 0 on success, -ERRNO if anything goes wrong.
 */
int amdgpu_mn_register(struct amdgpu_bo *bo, unsigned long addr)
{
	unsigned long end = addr + amdgpu_bo_size(bo) - 1;
	struct amdgpu_device *adev = amdgpu_ttm_adev(bo->tbo.bdev);
	enum amdgpu_mn_type type =
		bo->kfd_bo ? AMDGPU_MN_TYPE_HSA : AMDGPU_MN_TYPE_GFX;
	struct amdgpu_mn *amn;
	struct amdgpu_mn_node *node = NULL, *new_node;
	struct list_head bos;
	struct interval_tree_node *it;

	amn = amdgpu_mn_get(adev, type);
	if (IS_ERR(amn))
		return PTR_ERR(amn);

	new_node = kmalloc(sizeof(*new_node), GFP_KERNEL);
	if (!new_node)
		return -ENOMEM;

	INIT_LIST_HEAD(&bos);

	down_write(&amn->lock);

	while ((it = interval_tree_iter_first(&amn->objects, addr, end))) {
		kfree(node);
		node = container_of(it, struct amdgpu_mn_node, it);
		interval_tree_remove(&node->it, &amn->objects);
		addr = min(it->start, addr);
		end = max(it->last, end);
		list_splice(&node->bos, &bos);
	}

	if (!node)
		node = new_node;
	else
		kfree(new_node);

	bo->mn = amn;

	node->it.start = addr;
	node->it.last = end;
	INIT_LIST_HEAD(&node->bos);
	list_splice(&bos, &node->bos);
	list_add(&bo->mn_list, &node->bos);

	interval_tree_insert(&node->it, &amn->objects);

	up_write(&amn->lock);

	return 0;
}

/**
 * amdgpu_mn_unregister - unregister a BO for notifier updates
 *
 * @bo: amdgpu buffer object
 *
 * Remove any registration of MMU notifier updates from the buffer object.
 */
void amdgpu_mn_unregister(struct amdgpu_bo *bo)
{
	struct amdgpu_device *adev = amdgpu_ttm_adev(bo->tbo.bdev);
	struct amdgpu_mn *amn;
	struct list_head *head;

	mutex_lock(&adev->mn_lock);

	amn = bo->mn;
	if (amn == NULL) {
		mutex_unlock(&adev->mn_lock);
		return;
	}

	down_write(&amn->lock);

	/* save the next list entry for later */
	head = bo->mn_list.next;

	bo->mn = NULL;
	list_del_init(&bo->mn_list);

	if (list_empty(head)) {
		struct amdgpu_mn_node *node;

		node = container_of(head, struct amdgpu_mn_node, bos);
		interval_tree_remove(&node->it, &amn->objects);
		kfree(node);
	}

	up_write(&amn->lock);
	mutex_unlock(&adev->mn_lock);
}